Multi-objective optimization and quantum hybridization of equivariant deep learning interatomic potentials

Allegro is a machine learning interatomic potential model designed to predict atomic properties in molecules using E(3) equivariant neural networks. When training this model, there tends to be a trade-off between accuracy and inference time. For this reason, we apply multi-objective hyperparameter optimization to both objectives. Additionally, we experiment with modified architectures by constructing variants of Allegro: one extended with additional classical layers and one incorporating quantum–classical hybrid layers. We evaluate all models on QM9, rMD17-aspirin, rMD17-benzene, and a self-generated dataset of copper-lithium structures. As results, both variants surpass Allegro in force prediction accuracy across multiple datasets. The classical variant consistently improves over the baseline, while the quantum–classical hybrid variant achieves the best overall force prediction accuracy on the Cu-Li dataset, where it was fully optimized, outperforming the classical variant by approximately 13%. Notably, the hybrid variant also achieves competitive results on the remaining datasets despite using hyperparameters transferred from Cu-Li without dataset-specific optimization, suggesting that quantum–classical hybridization is a promising direction for enhancing MLIP architectures. • Multi-objective optimization of Allegro MLIP for accuracy and inference time. • Allegro+MLP and Allegro+QDI variants outperform vanilla Allegro on force MAE. • Quantum depth-infused hybrid model achieves 13% force MAE gain on Cu-Li. • Pareto fronts reveal accuracy–inference time trade-oHs across four datasets. • SAMO-COBRA efficiently optimizes 6–9 hyperparameters with 1200 evaluations.